File size: 19,706 Bytes
395201c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
{
    "gpt-4": {
        "max_tokens": 8192,
        "input_cost_per_token": 0.00003,
        "output_cost_per_token": 0.00006,
        "litellm_provider": "openai",
        "mode": "chat"
    },
    "gpt-4-0314": {
        "max_tokens": 8192,
        "input_cost_per_token": 0.00003,
        "output_cost_per_token": 0.00006,
        "litellm_provider": "openai",
        "mode": "chat"
    },
    "gpt-4-0613": {
        "max_tokens": 8192,
        "input_cost_per_token": 0.00003,
        "output_cost_per_token": 0.00006,
        "litellm_provider": "openai",
        "mode": "chat"
    },
    "gpt-4-32k": {
        "max_tokens": 32768,
        "input_cost_per_token": 0.00006,
        "output_cost_per_token": 0.00012,
        "litellm_provider": "openai",
        "mode": "chat"
    },
    "gpt-4-32k-0314": {
        "max_tokens": 32768,
        "input_cost_per_token": 0.00006,
        "output_cost_per_token": 0.00012,
        "litellm_provider": "openai",
        "mode": "chat"
    },
    "gpt-4-32k-0613": {
        "max_tokens": 32768,
        "input_cost_per_token": 0.00006,
        "output_cost_per_token": 0.00012,
        "litellm_provider": "openai",
        "mode": "chat"
    },
    "gpt-3.5-turbo": {
        "max_tokens": 4097,
        "input_cost_per_token": 0.0000015,
        "output_cost_per_token": 0.000002,
        "litellm_provider": "openai",
        "mode": "chat"
    },
    "gpt-3.5-turbo-0301": {
        "max_tokens": 4097,
        "input_cost_per_token": 0.0000015,
        "output_cost_per_token": 0.000002,
        "litellm_provider": "openai",
        "mode": "chat"
    },
    "gpt-3.5-turbo-0613": {
        "max_tokens": 4097,
        "input_cost_per_token": 0.0000015,
        "output_cost_per_token": 0.000002,
        "litellm_provider": "openai",
        "mode": "chat"
    },
    "gpt-3.5-turbo-16k": {
        "max_tokens": 16385,
        "input_cost_per_token": 0.000003,
        "output_cost_per_token": 0.000004,
        "litellm_provider": "openai",
        "mode": "chat"
    },
    "gpt-3.5-turbo-16k-0613": {
        "max_tokens": 16385,
        "input_cost_per_token": 0.000003,
        "output_cost_per_token": 0.000004,
        "litellm_provider": "openai",
        "mode": "chat"
    },
    "text-davinci-003": {
        "max_tokens": 4097,
        "input_cost_per_token": 0.000002,
        "output_cost_per_token": 0.000002,
        "litellm_provider": "text-completion-openai",
        "mode": "completion"
    },
    "text-curie-001": {
        "max_tokens": 2049,
        "input_cost_per_token": 0.000002,
        "output_cost_per_token": 0.000002,
        "litellm_provider": "text-completion-openai",
        "mode": "completion"
    },
    "text-babbage-001": {
        "max_tokens": 2049,
        "input_cost_per_token": 0.0000004,
        "output_cost_per_token": 0.0000004,
        "litellm_provider": "text-completion-openai",
        "mode": "completion"
    },
    "text-ada-001": {
        "max_tokens": 2049,
        "input_cost_per_token": 0.0000004,
        "output_cost_per_token": 0.0000004,
        "litellm_provider": "text-completion-openai",
        "mode": "completion"
    },
    "babbage-002": {
        "max_tokens": 16384,
        "input_cost_per_token": 0.0000004,
        "output_cost_per_token": 0.0000004,
        "litellm_provider": "text-completion-openai",
        "mode": "completion"
    },
    "davinci-002": {
        "max_tokens": 16384,
        "input_cost_per_token": 0.000002,
        "output_cost_per_token": 0.000002,
        "litellm_provider": "text-completion-openai",
        "mode": "completion"
    },    
    "gpt-3.5-turbo-instruct": {
        "max_tokens": 8192,
        "input_cost_per_token": 0.0000015,
        "output_cost_per_token": 0.000002,
        "litellm_provider": "text-completion-openai",
        "mode": "completion"
    },
    "claude-instant-1": {
        "max_tokens": 100000,
        "input_cost_per_token": 0.00000163,
        "output_cost_per_token": 0.00000551,
        "litellm_provider": "anthropic",
        "mode": "chat"
    },
    "claude-instant-1.2": {
        "max_tokens": 100000,
        "input_cost_per_token": 0.00000163,
        "output_cost_per_token": 0.00000551,
        "litellm_provider": "anthropic",
        "mode": "chat"
    },
    "claude-2": {
        "max_tokens": 100000,
        "input_cost_per_token": 0.00001102,
        "output_cost_per_token": 0.00003268,
        "litellm_provider": "anthropic",
        "mode": "chat"
    },
    "text-bison": {
        "max_tokens": 8192,
        "input_cost_per_token": 0.000000125,
        "output_cost_per_token": 0.000000125,
        "litellm_provider": "vertex_ai-text-models",
        "mode": "completion"
    },
    "text-bison@001": {
        "max_tokens": 8192,
        "input_cost_per_token": 0.000000125,
        "output_cost_per_token": 0.000000125,
        "litellm_provider": "vertex_ai-text-models",
        "mode": "completion"
    },
    "chat-bison": {
        "max_tokens": 4096,
        "input_cost_per_token": 0.000000125,
        "output_cost_per_token": 0.000000125,
        "litellm_provider": "vertex_ai-chat-models",
        "mode": "chat"
    },
    "chat-bison@001": {
        "max_tokens": 4096,
        "input_cost_per_token": 0.000000125,
        "output_cost_per_token": 0.000000125,
        "litellm_provider": "vertex_ai-chat-models",
        "mode": "chat"
    },
    "chat-bison-32k": {
        "max_tokens": 32000,
        "input_cost_per_token": 0.000000125,
        "output_cost_per_token": 0.000000125,
        "litellm_provider": "vertex_ai-chat-models",
        "mode": "chat"
    },
    "code-bison": {
        "max_tokens": 6144,
        "input_cost_per_token": 0.000000125,
        "output_cost_per_token": 0.000000125,
        "litellm_provider": "vertex_ai-code-text-models",
        "mode": "chat"
    },
    "code-bison@001": {
        "max_tokens": 6144,
        "input_cost_per_token": 0.000000125,
        "output_cost_per_token": 0.000000125,
        "litellm_provider": "vertex_ai-code-text-models",
        "mode": "completion"
    },
    "code-gecko@001": {
        "max_tokens": 2048,
        "input_cost_per_token": 0.000000125,
        "output_cost_per_token": 0.000000125,
        "litellm_provider": "vertex_ai-chat-models",
        "mode": "completion"
    },
    "code-gecko@latest": {
        "max_tokens": 2048,
        "input_cost_per_token": 0.000000125,
        "output_cost_per_token": 0.000000125,
        "litellm_provider": "vertex_ai-chat-models",
        "mode": "completion"
    },
    "codechat-bison": {
        "max_tokens": 6144,
        "input_cost_per_token": 0.000000125,
        "output_cost_per_token": 0.000000125,
        "litellm_provider": "vertex_ai-code-chat-models",
        "mode": "chat"
    },
    "codechat-bison@001": {
        "max_tokens": 6144,
        "input_cost_per_token": 0.000000125,
        "output_cost_per_token": 0.000000125,
        "litellm_provider": "vertex_ai-code-chat-models",
        "mode": "chat"
    },
    "codechat-bison-32k": {
        "max_tokens": 32000,
        "input_cost_per_token": 0.000000125,
        "output_cost_per_token": 0.000000125,
        "litellm_provider": "vertex_ai-chat-models",
        "mode": "chat"
    },
    "command-nightly": {
        "max_tokens": 4096,
        "input_cost_per_token": 0.000015,
        "output_cost_per_token": 0.000015,
        "litellm_provider": "cohere",
        "mode": "completion"
    },
     "command": {
        "max_tokens": 4096,
        "input_cost_per_token": 0.000015,
        "output_cost_per_token": 0.000015,
        "litellm_provider": "cohere",
        "mode": "completion"
    },
     "command-light": {
        "max_tokens": 4096,
        "input_cost_per_token": 0.000015,
        "output_cost_per_token": 0.000015,
        "litellm_provider": "cohere",
        "mode": "completion"
    },
     "command-medium-beta": {
        "max_tokens": 4096,
        "input_cost_per_token": 0.000015,
        "output_cost_per_token": 0.000015,
        "litellm_provider": "cohere",
        "mode": "completion"
    },
     "command-xlarge-beta": {
        "max_tokens": 4096,
        "input_cost_per_token": 0.000015,
        "output_cost_per_token": 0.000015,
        "litellm_provider": "cohere",
        "mode": "completion"
    },
    "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1": {
        "max_tokens": 4096,
        "litellm_provider": "replicate",
        "mode": "chat"
    },
    "openrouter/openai/gpt-3.5-turbo": {
        "max_tokens": 4095,
        "input_cost_per_token": 0.0000015,
        "output_cost_per_token": 0.000002,
        "litellm_provider": "openrouter",
        "mode": "chat"
    },
    "openrouter/openai/gpt-3.5-turbo-16k": {
        "max_tokens": 16383,
        "input_cost_per_token": 0.000003,
        "output_cost_per_token": 0.000004,
        "litellm_provider": "openrouter",
        "mode": "chat"
    },
    "openrouter/openai/gpt-4": {
        "max_tokens": 8192,
        "input_cost_per_token": 0.00003,
        "output_cost_per_token": 0.00006,
        "litellm_provider": "openrouter",
        "mode": "chat"
    },
    "openrouter/anthropic/claude-instant-v1": {
        "max_tokens": 100000,
        "input_cost_per_token": 0.00000163,
        "output_cost_per_token": 0.00000551,
        "litellm_provider": "openrouter",
        "mode": "chat"
    },
    "openrouter/anthropic/claude-2": {
        "max_tokens": 100000,
        "input_cost_per_token": 0.00001102,
        "output_cost_per_token": 0.00003268,
        "litellm_provider": "openrouter",
        "mode": "chat"
    },
    "openrouter/google/palm-2-chat-bison": {
        "max_tokens": 8000,
        "input_cost_per_token": 0.0000005,
        "output_cost_per_token": 0.0000005,
        "litellm_provider": "openrouter",
        "mode": "chat"
    },
    "openrouter/google/palm-2-codechat-bison": {
        "max_tokens": 8000,
        "input_cost_per_token": 0.0000005,
        "output_cost_per_token": 0.0000005,
        "litellm_provider": "openrouter",
        "mode": "chat"
    },
    "openrouter/meta-llama/llama-2-13b-chat": {
        "max_tokens": 4096,
        "input_cost_per_token": 0.0000002,
        "output_cost_per_token": 0.0000002,
        "litellm_provider": "openrouter",
        "mode": "chat"
    },
    "openrouter/meta-llama/llama-2-70b-chat": {
        "max_tokens": 4096,
        "input_cost_per_token": 0.0000015,
        "output_cost_per_token": 0.0000015,
        "litellm_provider": "openrouter",
        "mode": "chat"
    },
    "openrouter/meta-llama/codellama-34b-instruct": {
        "max_tokens": 8096,
        "input_cost_per_token": 0.0000005,
        "output_cost_per_token": 0.0000005,
        "litellm_provider": "openrouter",
        "mode": "chat"
    },
    "openrouter/nousresearch/nous-hermes-llama2-13b": {
        "max_tokens": 4096,
        "input_cost_per_token": 0.0000002,
        "output_cost_per_token": 0.0000002,
        "litellm_provider": "openrouter",
        "mode": "chat"
    },
    "openrouter/mancer/weaver": {
        "max_tokens": 8000,
        "input_cost_per_token": 0.000005625,
        "output_cost_per_token": 0.000005625,
        "litellm_provider": "openrouter",
        "mode": "chat"
    },
    "openrouter/gryphe/mythomax-l2-13b": {
        "max_tokens": 8192,
        "input_cost_per_token": 0.000001875,
        "output_cost_per_token": 0.000001875,
        "litellm_provider": "openrouter",
        "mode": "chat"
    },
    "openrouter/jondurbin/airoboros-l2-70b-2.1": {
        "max_tokens": 4096,
        "input_cost_per_token": 0.000013875,
        "output_cost_per_token": 0.000013875,
        "litellm_provider": "openrouter",
        "mode": "chat"
    },
    "openrouter/undi95/remm-slerp-l2-13b": {
        "max_tokens": 6144,
        "input_cost_per_token": 0.000001875,
        "output_cost_per_token": 0.000001875,
        "litellm_provider": "openrouter",
        "mode": "chat"
    },
    "openrouter/pygmalionai/mythalion-13b": {
        "max_tokens": 4096,
        "input_cost_per_token": 0.000001875,
        "output_cost_per_token": 0.000001875,
        "litellm_provider": "openrouter",
        "mode": "chat"
    },
    "openrouter/mistralai/mistral-7b-instruct": {
        "max_tokens": 4096,
        "input_cost_per_token": 0.0,
        "output_cost_per_token": 0.0,
        "litellm_provider": "openrouter",
        "mode": "chat"
    },
    "j2-ultra": {
        "max_tokens": 8192,
        "input_cost_per_token": 0.000015,
        "output_cost_per_token": 0.000015,
        "litellm_provider": "ai21",
        "mode": "completion"
    },
    "j2-mid": {
        "max_tokens": 8192,
        "input_cost_per_token": 0.00001,
        "output_cost_per_token": 0.00001,
        "litellm_provider": "ai21",
        "mode": "completion"
    },
    "j2-light": {
        "max_tokens": 8192,
        "input_cost_per_token": 0.000003,
        "output_cost_per_token": 0.000003,
        "litellm_provider": "ai21",
        "mode": "completion"
    },
    "dolphin": {
        "max_tokens": 4096,
        "input_cost_per_token": 0.00002,
        "output_cost_per_token": 0.00002,
        "litellm_provider": "nlp_cloud",
        "mode": "completion"
    },
    "chatdolphin": {
        "max_tokens": 4096,
        "input_cost_per_token": 0.00002,
        "output_cost_per_token": 0.00002,
        "litellm_provider": "nlp_cloud",
        "mode": "chat"
    },
    "luminous-base": {
        "max_tokens": 2048, 
        "input_cost_per_token": 0.00003,
        "output_cost_per_token": 0.000033,
        "litellm_provider": "aleph_alpha",
        "mode": "completion"
    },
    "luminous-base-control": {
        "max_tokens": 2048, 
        "input_cost_per_token": 0.0000375,
        "output_cost_per_token": 0.00004125,
        "litellm_provider": "aleph_alpha",
        "mode": "chat"
    },
    "luminous-extended": {
        "max_tokens": 2048, 
        "input_cost_per_token": 0.000045,
        "output_cost_per_token": 0.0000495,
        "litellm_provider": "aleph_alpha",
        "mode": "completion"
    },
    "luminous-extended-control": {
        "max_tokens": 2048, 
        "input_cost_per_token": 0.00005625,
        "output_cost_per_token": 0.000061875,
        "litellm_provider": "aleph_alpha",
        "mode": "chat"
    },
    "luminous-supreme": {
        "max_tokens": 2048, 
        "input_cost_per_token": 0.000175,
        "output_cost_per_token": 0.0001925,
        "litellm_provider": "aleph_alpha",
        "mode": "completion"
    },
    "luminous-supreme-control": {
        "max_tokens": 2048, 
        "input_cost_per_token": 0.00021875,
        "output_cost_per_token": 0.000240625,
        "litellm_provider": "aleph_alpha",
        "mode": "chat"
    },
    "ai21.j2-mid-v1": {
        "max_tokens": 8191, 
        "input_cost_per_token": 0.0000125,
        "output_cost_per_token": 0.0000125,
        "litellm_provider": "bedrock",
        "mode": "chat"
    },
    "ai21.j2-ultra-v1": {
        "max_tokens": 8191, 
        "input_cost_per_token": 0.0000188,
        "output_cost_per_token": 0.0000188,
        "litellm_provider": "bedrock",
        "mode": "chat"
    },
    "amazon.titan-text-lite-v1": {
        "max_tokens": 8000, 
        "input_cost_per_token": 0.0000003,
        "output_cost_per_token": 0.0000004,
        "litellm_provider": "bedrock",
        "mode": "chat"
    },
    "amazon.titan-text-express-v1": {
        "max_tokens": 8000, 
        "input_cost_per_token": 0.0000013,
        "output_cost_per_token": 0.0000017,
        "litellm_provider": "bedrock",
        "mode": "chat"
    },
    "anthropic.claude-v1": {
        "max_tokens": 100000, 
        "input_cost_per_token": 0.00001102,
        "output_cost_per_token": 0.00003268,
        "litellm_provider": "bedrock",
        "mode": "chat"
    },
    "anthropic.claude-v2": {
        "max_tokens": 100000, 
        "input_cost_per_token": 0.00001102,
        "output_cost_per_token": 0.00003268,
        "litellm_provider": "bedrock",
        "mode": "chat"
    },
    "anthropic.claude-instant-v1": {
        "max_tokens": 100000, 
        "input_cost_per_token": 0.00000163,
        "output_cost_per_token": 0.00000551,
        "litellm_provider": "bedrock",
        "mode": "chat"
    },
    "cohere.command-text-v14": {
        "max_tokens": 4096, 
        "input_cost_per_token": 0.0000015,
        "output_cost_per_token": 0.0000020,
        "litellm_provider": "bedrock",
        "mode": "chat"
    },
    "meta.llama2-13b-chat-v1": {
        "max_tokens": 4096, 
        "input_cost_per_token": 0.00000075,
        "output_cost_per_token": 0.000001,
        "litellm_provider": "bedrock",
        "mode": "chat"
    },
    "together-ai-up-to-3b": {
        "input_cost_per_token": 0.0000001,
        "output_cost_per_token": 0.0000001
    },
    "together-ai-3.1b-7b": {
        "input_cost_per_token": 0.0000002,
        "output_cost_per_token": 0.0000002
    },
    "together-ai-7.1b-20b": {
        "max_tokens": 1000,
        "input_cost_per_token": 0.0000004,
        "output_cost_per_token": 0.0000004
    },
    "together-ai-20.1b-40b": {
        "input_cost_per_token": 0.000001,
        "output_cost_per_token": 0.000001
    },
    "together-ai-40.1b-70b": {
        "input_cost_per_token": 0.000003,
        "output_cost_per_token": 0.000003
    },
    "ollama/llama2": {
        "max_tokens": 4096,
        "input_cost_per_token": 0.0,
        "output_cost_per_token": 0.0,
        "litellm_provider": "ollama",
        "mode": "completion"
    },
    "ollama/llama2:13b": {
        "max_tokens": 4096,
        "input_cost_per_token": 0.0,
        "output_cost_per_token": 0.0,
        "litellm_provider": "ollama",
        "mode": "completion"
    },
    "ollama/llama2:70b": {
        "max_tokens": 4096,
        "input_cost_per_token": 0.0,
        "output_cost_per_token": 0.0,
        "litellm_provider": "ollama",
        "mode": "completion"
    },
    "ollama/llama2-uncensored": {
        "max_tokens": 4096,
        "input_cost_per_token": 0.0,
        "output_cost_per_token": 0.0,
        "litellm_provider": "ollama",
        "mode": "completion"
    },
    "deepinfra/meta-llama/Llama-2-70b-chat-hf": {
        "max_tokens": 6144,
        "input_cost_per_token": 0.000001875,
        "output_cost_per_token": 0.000001875,
        "litellm_provider": "deepinfra",
        "mode": "chat"
    },
    "deepinfra/codellama/CodeLlama-34b-Instruct-hf": {
        "max_tokens": 4096,
        "input_cost_per_token": 0.0000006,
        "output_cost_per_token": 0.0000006,
        "litellm_provider": "deepinfra",
        "mode": "chat"
      },
      "deepinfra/meta-llama/Llama-2-13b-chat-hf": {
        "max_tokens": 4096,
        "input_cost_per_token": 0.00000035,
        "output_cost_per_token": 0.00000035,
        "litellm_provider": "deepinfra",
        "mode": "chat"
      },
      "deepinfra/meta-llama/Llama-2-7b-chat-hf": {
        "max_tokens": 4096,
        "input_cost_per_token": 0.0000002,
        "output_cost_per_token": 0.0000002,
        "litellm_provider": "deepinfra",
        "mode": "chat"
      },
      "deepinfra/mistralai/Mistral-7B-Instruct-v0.1": {
        "max_tokens": 4096,
        "input_cost_per_token": 0.0000002,
        "output_cost_per_token": 0.0000002,
        "litellm_provider": "deepinfra",
        "mode": "chat"
      },
      "deepinfra/jondurbin/airoboros-l2-70b-gpt4-1.4.1": {
        "max_tokens": 4096,
        "input_cost_per_token": 0.0000007,
        "output_cost_per_token": 0.00000095,
        "litellm_provider": "deepinfra",
        "mode": "chat"
      }
}